From db0397cfaaf488364e3d2e1669dfefae2ee6ea73 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 14 Dec 2015 19:57:10 +0000
Subject: [PATCH] shortcut layers, msr networks
---
src/data.c | 247 ++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 201 insertions(+), 46 deletions(-)
diff --git a/src/data.c b/src/data.c
index a335e07..8d76276 100644
--- a/src/data.c
+++ b/src/data.c
@@ -1,6 +1,7 @@
#include "data.h"
#include "utils.h"
#include "image.h"
+#include "cuda.h"
#include <stdio.h>
#include <stdlib.h>
@@ -53,7 +54,12 @@
X.cols = 0;
for(i = 0; i < n; ++i){
- image im = load_image(paths[i], w, h, 1);
+ image im = load_image(paths[i], w, h, 3);
+
+ image gray = grayscale_image(im);
+ free_image(im);
+ im = gray;
+
X.vals[i] = im.data;
X.cols = im.h*im.w*im.c;
}
@@ -76,12 +82,6 @@
return X;
}
-typedef struct{
- int id;
- float x,y,w,h;
- float left, right, top, bottom;
-} box_label;
-
box_label *read_boxes(char *filename, int *n)
{
box_label *boxes = calloc(1, sizeof(box_label));
@@ -149,10 +149,13 @@
}
}
-void fill_truth_region(char *path, float *truth, int classes, int num_boxes, int flip, float dx, float dy, float sx, float sy)
+void fill_truth_swag(char *path, float *truth, int classes, int flip, float dx, float dy, float sx, float sy)
{
char *labelpath = find_replace(path, "images", "labels");
+ labelpath = find_replace(labelpath, "JPEGImages", "labels");
+
labelpath = find_replace(labelpath, ".jpg", ".txt");
+ labelpath = find_replace(labelpath, ".JPG", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
@@ -162,42 +165,69 @@
int id;
int i;
- for(i = 0; i < num_boxes*num_boxes*(4+classes); i += 4+classes){
- truth[i] = 1;
- }
-
- for(i = 0; i < count; ++i){
- x = boxes[i].x;
- y = boxes[i].y;
- w = boxes[i].w;
- h = boxes[i].h;
+ for (i = 0; i < count && i < 30; ++i) {
+ x = boxes[i].x;
+ y = boxes[i].y;
+ w = boxes[i].w;
+ h = boxes[i].h;
id = boxes[i].id;
- if (x <= 0 || x >= 1 || y <= 0 || y >= 1) continue;
+ if (w < .0 || h < .0) continue;
+
+ int index = (4+classes) * i;
+
+ truth[index++] = x;
+ truth[index++] = y;
+ truth[index++] = w;
+ truth[index++] = h;
+
+ if (id < classes) truth[index+id] = 1;
+ }
+ free(boxes);
+}
+
+void fill_truth_region(char *path, float *truth, int classes, int num_boxes, int flip, float dx, float dy, float sx, float sy)
+{
+ char *labelpath = find_replace(path, "images", "labels");
+ labelpath = find_replace(labelpath, "JPEGImages", "labels");
+
+ labelpath = find_replace(labelpath, ".jpg", ".txt");
+ labelpath = find_replace(labelpath, ".JPG", ".txt");
+ labelpath = find_replace(labelpath, ".JPEG", ".txt");
+ int count = 0;
+ box_label *boxes = read_boxes(labelpath, &count);
+ randomize_boxes(boxes, count);
+ correct_boxes(boxes, count, dx, dy, sx, sy, flip);
+ float x,y,w,h;
+ int id;
+ int i;
+
+ for (i = 0; i < count; ++i) {
+ x = boxes[i].x;
+ y = boxes[i].y;
+ w = boxes[i].w;
+ h = boxes[i].h;
+ id = boxes[i].id;
+
if (w < .01 || h < .01) continue;
int col = (int)(x*num_boxes);
int row = (int)(y*num_boxes);
- float xa = (col+.5)/num_boxes;
- float ya = (row+.5)/num_boxes;
- float wa = .5;
- float ha = .5;
+ x = x*num_boxes - col;
+ y = y*num_boxes - row;
- float tx = (x - xa) / wa;
- float ty = (y - ya) / ha;
- float tw = log2(w/wa);
- float th = log2(h/ha);
+ int index = (col+row*num_boxes)*(5+classes);
+ if (truth[index]) continue;
+ truth[index++] = 1;
- int index = (col+row*num_boxes)*(4+classes);
- if(!truth[index]) continue;
- truth[index] = 0;
- truth[index+id+1] = 1;
+ if (id < classes) truth[index+id] = 1;
index += classes;
- truth[index++] = tx;
- truth[index++] = ty;
- truth[index++] = tw;
- truth[index++] = th;
+
+ truth[index++] = x;
+ truth[index++] = y;
+ truth[index++] = w;
+ truth[index++] = h;
}
free(boxes);
}
@@ -375,7 +405,7 @@
}
}
-data load_data_region(int n, char **paths, int m, int classes, int w, int h, int num_boxes)
+data load_data_region(int n, char **paths, int m, int w, int h, int size, int classes, float jitter)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
@@ -386,7 +416,7 @@
d.X.vals = calloc(d.X.rows, sizeof(float*));
d.X.cols = h*w*3;
- int k = num_boxes*num_boxes*(4+classes);
+ int k = size*size*(5+classes);
d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){
image orig = load_image_color(random_paths[i], 0, 0);
@@ -394,8 +424,8 @@
int oh = orig.h;
int ow = orig.w;
- int dw = ow/10;
- int dh = oh/10;
+ int dw = (ow*jitter);
+ int dh = (oh*jitter);
int pleft = (rand_uniform() * 2*dw - dw);
int pright = (rand_uniform() * 2*dw - dw);
@@ -418,7 +448,7 @@
if(flip) flip_image(sized);
d.X.vals[i] = sized.data;
- fill_truth_region(random_paths[i], d.y.vals[i], classes, num_boxes, flip, dx, dy, 1./sx, 1./sy);
+ fill_truth_region(random_paths[i], d.y.vals[i], classes, size, flip, dx, dy, 1./sx, 1./sy);
free_image(orig);
free_image(cropped);
@@ -427,6 +457,121 @@
return d;
}
+data load_data_compare(int n, char **paths, int m, int classes, int w, int h)
+{
+ if(m) paths = get_random_paths(paths, 2*n, m);
+ int i,j;
+ data d;
+ d.shallow = 0;
+
+ d.X.rows = n;
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
+ d.X.cols = h*w*6;
+
+ int k = 2*(classes);
+ d.y = make_matrix(n, k);
+ for(i = 0; i < n; ++i){
+ image im1 = load_image_color(paths[i*2], w, h);
+ image im2 = load_image_color(paths[i*2+1], w, h);
+
+ d.X.vals[i] = calloc(d.X.cols, sizeof(float));
+ memcpy(d.X.vals[i], im1.data, h*w*3*sizeof(float));
+ memcpy(d.X.vals[i] + h*w*3, im2.data, h*w*3*sizeof(float));
+
+ int id;
+ float iou;
+
+ char *imlabel1 = find_replace(paths[i*2], "imgs", "labels");
+ imlabel1 = find_replace(imlabel1, "jpg", "txt");
+ FILE *fp1 = fopen(imlabel1, "r");
+
+ while(fscanf(fp1, "%d %f", &id, &iou) == 2){
+ if (d.y.vals[i][2*id] < iou) d.y.vals[i][2*id] = iou;
+ }
+
+ char *imlabel2 = find_replace(paths[i*2+1], "imgs", "labels");
+ imlabel2 = find_replace(imlabel2, "jpg", "txt");
+ FILE *fp2 = fopen(imlabel2, "r");
+
+ while(fscanf(fp2, "%d %f", &id, &iou) == 2){
+ if (d.y.vals[i][2*id + 1] < iou) d.y.vals[i][2*id + 1] = iou;
+ }
+
+ for (j = 0; j < classes; ++j){
+ if (d.y.vals[i][2*j] > .5 && d.y.vals[i][2*j+1] < .5){
+ d.y.vals[i][2*j] = 1;
+ d.y.vals[i][2*j+1] = 0;
+ } else if (d.y.vals[i][2*j] < .5 && d.y.vals[i][2*j+1] > .5){
+ d.y.vals[i][2*j] = 0;
+ d.y.vals[i][2*j+1] = 1;
+ } else {
+ d.y.vals[i][2*j] = SECRET_NUM;
+ d.y.vals[i][2*j+1] = SECRET_NUM;
+ }
+ }
+ fclose(fp1);
+ fclose(fp2);
+
+ free_image(im1);
+ free_image(im2);
+ }
+ if(m) free(paths);
+ return d;
+}
+
+data load_data_swag(char **paths, int n, int classes, float jitter)
+{
+ int index = rand_r(&data_seed)%n;
+ char *random_path = paths[index];
+
+ image orig = load_image_color(random_path, 0, 0);
+ int h = orig.h;
+ int w = orig.w;
+
+ data d;
+ d.shallow = 0;
+ d.w = w;
+ d.h = h;
+
+ d.X.rows = 1;
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
+ d.X.cols = h*w*3;
+
+ int k = (4+classes)*30;
+ d.y = make_matrix(1, k);
+
+ int dw = w*jitter;
+ int dh = h*jitter;
+
+ int pleft = (rand_uniform() * 2*dw - dw);
+ int pright = (rand_uniform() * 2*dw - dw);
+ int ptop = (rand_uniform() * 2*dh - dh);
+ int pbot = (rand_uniform() * 2*dh - dh);
+
+ int swidth = w - pleft - pright;
+ int sheight = h - ptop - pbot;
+
+ float sx = (float)swidth / w;
+ float sy = (float)sheight / h;
+
+ int flip = rand_r(&data_seed)%2;
+ image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
+
+ float dx = ((float)pleft/w)/sx;
+ float dy = ((float)ptop /h)/sy;
+
+ image sized = resize_image(cropped, w, h);
+ if(flip) flip_image(sized);
+ d.X.vals[0] = sized.data;
+
+ fill_truth_swag(random_path, d.y.vals[0], classes, flip, dx, dy, 1./sx, 1./sy);
+
+ free_image(orig);
+ free_image(cropped);
+
+ return d;
+}
+
data load_data_detection(int n, char **paths, int m, int classes, int w, int h, int num_boxes, int background)
{
char **random_paths = get_random_paths(paths, n, m);
@@ -488,14 +633,26 @@
void *load_thread(void *ptr)
{
- printf("Loading data: %d\n", rand_r(&data_seed));
+
+#ifdef GPU
+ cudaError_t status = cudaSetDevice(gpu_index);
+ check_error(status);
+#endif
+
+ //printf("Loading data: %d\n", rand_r(&data_seed));
load_args a = *(struct load_args*)ptr;
if (a.type == CLASSIFICATION_DATA){
*a.d = load_data(a.paths, a.n, a.m, a.labels, a.classes, a.w, a.h);
} else if (a.type == DETECTION_DATA){
*a.d = load_data_detection(a.n, a.paths, a.m, a.classes, a.w, a.h, a.num_boxes, a.background);
+ } else if (a.type == WRITING_DATA){
+ *a.d = load_data_writing(a.paths, a.n, a.m, a.w, a.h, a.out_w, a.out_h);
} else if (a.type == REGION_DATA){
- *a.d = load_data_region(a.n, a.paths, a.m, a.classes, a.w, a.h, a.num_boxes);
+ *a.d = load_data_region(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes, a.jitter);
+ } else if (a.type == SWAG_DATA){
+ *a.d = load_data_swag(a.paths, a.n, a.classes, a.jitter);
+ } else if (a.type == COMPARE_DATA){
+ *a.d = load_data_compare(a.n, a.paths, a.m, a.classes, a.w, a.h);
} else if (a.type == IMAGE_DATA){
*(a.im) = load_image_color(a.path, 0, 0);
*(a.resized) = resize_image(*(a.im), a.w, a.h);
@@ -509,20 +666,18 @@
pthread_t thread;
struct load_args *ptr = calloc(1, sizeof(struct load_args));
*ptr = args;
- if(pthread_create(&thread, 0, load_thread, ptr)) {
- error("Thread creation failed");
- }
+ if(pthread_create(&thread, 0, load_thread, ptr)) error("Thread creation failed");
return thread;
}
-data load_data_writing(char **paths, int n, int m, int w, int h)
+data load_data_writing(char **paths, int n, int m, int w, int h, int out_w, int out_h)
{
if(m) paths = get_random_paths(paths, n, m);
char **replace_paths = find_replace_paths(paths, n, ".png", "-label.png");
data d;
d.shallow = 0;
d.X = load_image_paths(paths, n, w, h);
- d.y = load_image_paths_gray(replace_paths, n, w/8, h/8);
+ d.y = load_image_paths_gray(replace_paths, n, out_w, out_h);
if(m) free(paths);
int i;
for(i = 0; i < n; ++i) free(replace_paths[i]);
--
Gitblit v1.10.0